Skip to main content

Posts

Showing posts with the label llm

Build Flexible AI Agents With The Genkit Framework

  Genkit is Google's open-source framework designed for building full-stack, AI-powered and agentic applications. Genkit is a set of modular building blocks that help you transition from making simple model requests to creating highly autonomous, reliable and production-ready AI systems. To understand what it offers you must compare it to how one builds AI applications at the moment. https://www.i-programmer.info/news/105-artificial-intelligence/19032-build-flexible-ai-agents-with-the-genkit-framework.html

DeepSWE - Best Benchmark For Evaluating AI Coding Agents?

  DeepSWE is a high-fidelity benchmarking platform designed to evaluate the performance of frontier AI coding agents on complex long-horizon software engineering tasks. Unlike traditional benchmarks that reuse existing GitHub data, this system utilizes original, contamination-free tasks across five major programming languages to prevent models from relying on memorized solutions, creating a much clearer separation between frontier coding models than older public benchmarks like SWE-bench. https://www.i-programmer.info/news/105-artificial-intelligence/19016-deepswe-best-benchmark-for-evaluating-ai-coding-agents.html

RAMPART and Clarity Secure Your AI Agents

  RAMPART and Clarity are frameworks designed by Microsoft to evaluate the safety and security of agentic AI applications. RAMPART (Risk Assessment & Measurement Platform for Agentic Red Teaming), is built on top of Microsoft's PyRIT (Python Risk Identification Tool) primitives. Rather than treating AI safety as a one-time post-build review, it allows developers to write safety and security tests as repeatable code th https://www.i-programmer.info/news/105-artificial-intelligence/19001-rampart-and-clarity-secure-your-ai-agents.html

What Happened At AI-fokus 2026

  AI-fokus, a spin off of Jfokus, is a conference focusing  on the evolution of agentic AI and its practical implementation in software development. https://www.i-programmer.info/news/105-artificial-intelligence/18981-what-happened-at-ai-fokus-2026.html

The Agent Toolkit For AWS

  The Agent Toolkit for AWS is a comprehensive suite of developer tools designed to help AI coding agents build, deploy, and manage cloud applications more effectively. https://www.i-programmer.info/news/141-cloud-computing/18898-the-agent-toolkit-for-aws.html

Monocle: A Framework for Tracing GenAI Application Code

  Monocle is a community-driven, open-source framework designed to monitor and trace generative AI applications by capturing data compliant with the OpenTelemetry ecosystem. Governing its development through the Linux Foundation, the project provides specialized tools for developers and platform engineers to instrument code in Python and TypeScript without requiring extensive manual code decoration. https://www.i-programmer.info/news/80-java/18892-monocle-a-framework-for-tracing-genai-application-code.html

Integrating Neo4j and Gemini CLI

  We explore a combination that opens new ways of interacting with the Neo4j Graph database. The Neo4j Gemini CLI extension integrates Gemini's capabilities directly into your terminal by bundling four Neo4j Model Context Protocol servers. This integration bridges the AI's reasoning engine with Neo4j, allowing you to deploy infrastructure, write queries, and build GraphRAG applications using natural language without leaving your terminal. https://www.i-programmer.info/news/90-tools/18886-integrating-neo4j-and-gemini-cli-.html

Massachusetts' Institute of Technology Introduction to Deep Learning

  The full materials of the MIT 6.S191 lecture which took place just this March are now available for free and for all. This lecture is a comprehensive overview of deep learning architectures, specifically focusing on Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. https://www.i-programmer.info/news/150-training-a-education/18878-massachusetts-institute-of-technology-introduction-to-deep-learning.html

Jupyter Notebooks MCP Server

  Jupyter gets its own MCP server. The Jupyter MCP Server by Datalayer is a Model Context Protocol server implementation designed to act as a bridge between Large Language Models, AI assistants and a user's live Jupyter environment. What does it enable? https://www.i-programmer.info/news/90-tools/18875-jupyter-notebooks-mcp-server-.html

The .NET Agent Skills

  Microsoft's extends the capabilities of the AI coding agents through Agent Skills for .NET framework-oriented tasks. But first of all, what are Agent Skills? Agent Skills are a lightweight, open, and standardized format used to extend AI agents' capabilities with specialized knowledge and workflows https://www.i-programmer.info/news/89-net/18867-the-net-agent-skills.html

Agentic Skills For The Database

  Companies like PlanetScale and Oracle are providing curated libraries of Skills that allow AI coding assistants, such as Claude Code or Cursor, to interact directly with databases. Skills, Skills, Skills...the latest buzzword in this era of AI induced coding practices. This time they come for the Database to enable agents to perform complex tasks like automated schema optimization, security audits and CSV data ingestion with higher precision and lower token consumption. https://www.i-programmer.info/news/90-tools/18846-agentic-skills-for-the-database-.html

GitHub Copilot CLI For Beginners - The Course

  It's a full curriculum that lives solely on its Github repository. And it's really full; it spans from installation basics to advanced production workflows which also include Agent Skills for automating team standards, specialized agents for targeted expertise, and the Model Context Protocol (MCP) for connecting the AI to external data sources like GitHub repositories and live documentation. https://www.i-programmer.info/news/150-training-a-education/18824-github-copilot-cli-for-beginners-the-course-.html